Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2922. Min Act: -0.0000

Data Index: 41080 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1064586 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1188075 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2044. Min Act: -0.0000

Data Index: 49280 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2271. Min Act: -0.0001

Data Index: 981763 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1098266 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1747. Min Act: -0.0001

Data Index: 990290 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2173. Min Act: -0.0000

Data Index: 840853 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1724. Min Act: -0.0000

Data Index: 558804 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1926. Min Act: -0.0000

Data Index: 595512 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1791. Min Act: -0.0001

Data Index: 9856 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1825. Min Act: -0.0000

Data Index: 829691 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1927. Min Act: -0.0000

Data Index: 968642 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1962. Min Act: -0.0000

Data Index: 845327 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1816. Min Act: -0.0000

Data Index: 277451 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1559. Min Act: -0.0001

Data Index: 583083 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1840. Min Act: -0.0000

Data Index: 804414 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1646. Min Act: -0.0001

Data Index: 269305 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2084. Min Act: -0.0000

Data Index: 202400 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1796. Min Act: -0.0000

Data Index: 42524 (C4 (Web Text))

Max Activating Token Index: 481